Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,10 @@ Qwen2.5-Coder-7B-Instruct trained on a merged dataset of Unity3d q&a from these
|
|
| 21 |
[ibranze/codellama_unity3d_v2](https://huggingface.co/datasets/ibranze/codellama_unity3d_v2) (Full)
|
| 22 |
[Hypersniper/unity_api_2022_3](https://huggingface.co/datasets/Hypersniper/unity_api_2022_3) (5%)
|
| 23 |
|
| 24 |
-
15062 rows in total with a 10% validation split
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
Consider this a preview as I develop a dataset of my own that I'm pleased with.
|
| 27 |
|
|
|
|
| 21 |
[ibranze/codellama_unity3d_v2](https://huggingface.co/datasets/ibranze/codellama_unity3d_v2) (Full)
|
| 22 |
[Hypersniper/unity_api_2022_3](https://huggingface.co/datasets/Hypersniper/unity_api_2022_3) (5%)
|
| 23 |
|
| 24 |
+
15062 rows in total with a 10% validation split.
|
| 25 |
+
|
| 26 |
+
Trained with native chat template (minus tools usage, see this issue: https://github.com/unslothai/unsloth/issues/1053). With a little superficial testing done, it seems to respond well to the mistral template.
|
| 27 |
+
|
| 28 |
|
| 29 |
Consider this a preview as I develop a dataset of my own that I'm pleased with.
|
| 30 |
|